Research
Research papers and technical publications
Quantum Alignment: A New Paradigm for AI Safety
Exploring quantum-inspired approaches to align advanced AI systems with human values and intentions.
Mechanistic Interpretability in Large Language Models
Understanding internal representations and computational mechanisms in transformer-based language models.
Advanced Safety Protocols for AGI Systems
Research on comprehensive safety measures for advanced AI systems (English only).
Scaling Laws for Neural Language Models
An empirical study of how language model performance scales with model size, dataset size, and compute.